diff --git a/docker/llm/inference-cpp/Dockerfile b/docker/llm/inference-cpp/Dockerfile
index 0645e351..f738e4f7 100644
--- a/docker/llm/inference-cpp/Dockerfile
+++ b/docker/llm/inference-cpp/Dockerfile
@@ -44,7 +44,20 @@ RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRO
     pip install transformers_stream_generator einops tiktoken && \
     # Install opencl-related repos
     apt-get update && \
-    apt-get install -y --no-install-recommends intel-opencl-icd intel-level-zero-gpu=1.3.26241.33-647~22.04 level-zero level-zero-dev --allow-downgrades && \
+    # apt-get install -y --no-install-recommends intel-opencl-icd intel-level-zero-gpu=1.3.26241.33-647~22.04 level-zero level-zero-dev --allow-downgrades && \
+    mkdir -p /tmp/gpu && \
+    cd /tmp/gpu && \
+    wget https://github.com/oneapi-src/level-zero/releases/download/v1.18.3/level-zero_1.18.3+u22.04_amd64.deb && \
+    wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.17791.9/intel-igc-core_1.0.17791.9_amd64.deb && \
+    wget https://github.com/intel/intel-graphics-compiler/releases/download/igc-1.0.17791.9/intel-igc-opencl_1.0.17791.9_amd64.deb && \
+    wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/intel-level-zero-gpu_1.6.31294.12_amd64.deb && \
+    wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/intel-opencl-icd_24.39.31294.12_amd64.deb && \
+    wget https://github.com/intel/compute-runtime/releases/download/24.39.31294.12/libigdgmm12_22.5.2_amd64.deb && \
+    dpkg -i *.deb && \
+    rm *.deb && \
+    rm -rf /tmp/gpu && \
+    mkdir -p /llm && \
+    cd /llm && \
     # Install Dependencies
     # remove blinker to avoid error
     find /usr/lib/python3/dist-packages/ -name 'blinker*' -exec rm -rf {} + && \